On statistical arbitrage under a conditional factor model of equity returns
Study on statistical arbitrage using a conditional factor model for US equities, demonstrating competitive performance over 29 years.
What it examines
This paper presents a conditional factor model for U.S. equity returns within a state space framework to analyze statistical arbitrage trading strategies. It aims to estimate fair value using asset-wise factor exposures and latent factor vectors, comparing linear and non-linear models over a 29-year period.
What it concludes
The research suggests that the conditional factor model in a state space framework is a robust approach for statistical arbitrage. Future work could explore alternative data, non-linear factor models, and intraday time scales to enhance performance. Potential applications include hedge funds and quantitative trading strategies.
Evidence objects
The research suggests that the conditional factor model in a state space framework is a robust approach for statistical arbitrage. Future work could explore alternative data, non-linear factor models, and intraday time scales to enhance performance. Potential applications include hedge funds and quantitative trading strategies.
key_findings bullet 1 · key_findings · validation V0
Raw abstract and provenance
Abstract: We consider a conditional factor model for a multivariate portfolio of United States equities in the context of analysing a statistical arbitrage trading strategy. A state space framework underlies the factor model whereby asset returns are assumed to be a noisy observation of a linear combination of factor values and latent factor risk premia. Filter and state prediction estimates for the risk pr… ▽ More We consider a conditional factor model for a multivariate portfolio of United States equities in the context of analysing a statistical arbitrage trading strategy. A state space framework underlies the factor model whereby asset returns are assumed to be a noisy observation of a linear combination of factor values and latent factor risk premia. Filter and state prediction estimates for the risk premia are retrieved in an online way. Such estimates induce filtered asset returns that can be compared to measurement observations, with large deviations representing candidate mean reversion trades. Further, in that the risk premia are modelled as time-varying quantities, non-stationarity in returns is de facto captured. We study an empirical trading strategy respectful of transaction costs, and demonstrate performance over a long history of 29 years, for both a linear and a non-linear state space model. Our results show that the model is competitive relative to the results of other methods, including simple benchmarks and other cutting-edge approaches as published in the literature. Also of note, while strategy performance degradation is noticed through time -- especially for the most recent years -- the strategy continues to offer compelling economics, and has scope for further advancement. △ Less
Source row: 1462 · abstract type: unknown